IAUnet: Global Context-Aware Feature Learning for Person Reidentification | |
Hou, Ruibing1,2; Ma, Bingpeng2; Chang, Hong1,2; Gu, Xinqian1,2; Shan, Shiguang1,2,3; Chen, Xilin1,2 | |
刊名 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS |
2021-10-01 | |
卷号 | 32期号:10页码:4460-4474 |
关键词 | Context modeling Feature extraction Computational modeling Semantics Aggregates Visualization Task analysis Feature enhancing interaction-aggregation person reidentification (reID) spatial-temporal context modeling |
ISSN号 | 2162-237X |
DOI | 10.1109/TNNLS.2020.3017939 |
英文摘要 | Person reidentification (reID) by convolutional neural network (CNN)-based networks has achieved favorable performance in recent years. However, most of existing CNN-based methods do not take full advantage of spatial-temporal context modeling. In fact, the global spatial-temporal context can greatly clarify local distractions to enhance the target feature representation. To comprehensively leverage the spatial-temporal context information, in this work, we present a novel block, interaction-aggregation-update (IAU), for high-performance person reID. First, the spatial-temporal IAU (STIAU) module is introduced. STIAU jointly incorporates two types of contextual interactions into a CNN framework for target feature learning. Here, the spatial interactions learn to compute the contextual dependencies between different body parts of a single frame, while the temporal interactions are used to capture the contextual dependencies between the same body parts across all frames. Furthermore, a channel IAU (CIAU) module is designed to model the semantic contextual interactions between channel features to enhance the feature representation, especially for small-scale visual cues and body parts. Therefore, the IAU block enables the feature to incorporate the globally spatial, temporal, and channel context. It is lightweight, end-to-end trainable, and can be easily plugged into existing CNNs to form IAUnet. The experiments show that IAUnet performs favorably against state of the art on both image and video reID tasks and achieves compelling results on a general object categorization task. The source code is available at https://github.com/blue-blue272/ImgReID-IAnet. |
资助项目 | Natural Science Foundation of China (NSFC)[61732004] ; Natural Science Foundation of China (NSFC)[61876171] ; Natural Science Foundation of China (NSFC)[61976203] ; Fundamental Research Funds for the Central Universities |
WOS研究方向 | Computer Science ; Engineering |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000704111000018 |
内容类型 | 期刊论文 |
源URL | [http://119.78.100.204/handle/2XEOYT63/17019] |
专题 | 中国科学院计算技术研究所 |
通讯作者 | Ma, Bingpeng |
作者单位 | 1.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China 3.CAS Ctr Excellence Brain Sci & Intelligence Techn, Shanghai 200031, Peoples R China |
推荐引用方式 GB/T 7714 | Hou, Ruibing,Ma, Bingpeng,Chang, Hong,et al. IAUnet: Global Context-Aware Feature Learning for Person Reidentification[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2021,32(10):4460-4474. |
APA | Hou, Ruibing,Ma, Bingpeng,Chang, Hong,Gu, Xinqian,Shan, Shiguang,&Chen, Xilin.(2021).IAUnet: Global Context-Aware Feature Learning for Person Reidentification.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,32(10),4460-4474. |
MLA | Hou, Ruibing,et al."IAUnet: Global Context-Aware Feature Learning for Person Reidentification".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 32.10(2021):4460-4474. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论